Custom agents

A Lean quality system for AI-assisted work — every defect becomes a permanent countermeasure. Built by a manufacturing operator.

PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.

Open benchmarks for browser agents: BU Bench V2.1, 200 real web tasks. Rerun them with your own API keys.

Long-document search with Jev and PageIndex

原作から脚本・画像生成・組版・PDF出力まで進める、Codex向け漫画制作ツール

个人微信号自动回复、陪聊、查天气、查垃圾分类。新增查看今日新闻和知乎热榜功能。

A comprehensive, production-ready framework for building intelligent AI agents with advanced capabilities including tool calling, persistent memory, intelligent concurrency, and event-driven observability

An AIO Discord bot for sneaker groups

Multi-turn dialogue baselines written in PyTorch

Integrate user-agent detection in an idiomatic React way

AI-driven web automation agent that uses Playwright for browser interactions and LLM integration for intelligent decision-making. It's designed for reliable, adaptable web automation with robust element detection and contextual understanding. It's single agent by design, and it is built with getting solid benefit out of smaller models in mind.

Build Secure and Compliant AI agents and MCP Servers. YC W23

[MTI-LLM@NeurIPS 2025] Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."

Run Surfer-H agents powered by Holo1 using the Surfer-H-CLI. Includes example tasks, scripts, and configurations.

Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.

🪐 🤖 AI Agents with 🔧 MCP tools and 🧰 Skills for JupyterLab — Chat with your Notebook and execute code.

Git For database Systems

Read books the way Feynman did — along with a continuously evolving network of agent-simulated great minds

The agent OS that evolves itself.

A comprehensive list of top best AI agents directories available online

Open Framework for AI Agents to play Red Alert through Reinforcement Learning

This is a collection of various Generative AI projects and AI Agents exploring the realms of Images, code, text, and more

Vibe Island — macOS notch panel for 25 AI coding agents: Claude Code, Codex, Cursor, Gemini CLI & more. Monitor, approve, and jump back from the notch. Community home: bug reports & feature requests.

Agent Memory Benchmark

Rust-native MCP server for Office document processing (Excel, Word, PowerPoint). Sub-millisecond, local-first, open source.

Desktop app for harness engineering, loop engineering, graph engineering—and whatever comes next in local AI-agent workflows.

Agentic text-to-SQL SDK: hand the LLM one execute_sql tool and let it explore the schema, test queries, and self-correct — no RAG, no semantic layer. 20/20 on an 80-table Spider run. Built-in tracing and scenario support.

build eval for your agent in 10 mins

Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

【Codex PCB Layout Skill】GPT-6 Astra/Sol x KiCad10. PCB 自动布线 Skill（涵盖通用规则，DDR，USB，CAN等各类接口的 ESD 器件泄放路径等专项规则）

Chat with your documents to create and refine editable architecture diagrams. Local workspace, Excalidraw canvas, optional Tavily search.

JanusX — open-source AI-coding workspace: worktree parallel dev, split terminals for Claude/Codex/OpenCode/Pi, checkpoints with diff-restore, Blueprint+Island. Second test Oct 20 in progress (not v1.0) | 开源AI编程桌面：多分支并行、分屏终端、还原点、蓝图，10.20二测中

A plugin runtime for software that iterates on itself — the substrate where agents write, swap and hot-reload their own plugins in Rust, TypeScript, Python and Go, across processes and machines.

Tauri 2 + React desktop app: VSCode-style file tree, live Excel/Word/PPT preview (OfficeCLI), and AI chat editing of Office files via @aipack-ai/agent.

mutual layer for multiple agents from different environment or providers to work on same interface or device, toward the same final goal

A very simple implementation of a service for a mattermost bot that uses ChatGPT in the backend.

One install. Shared memory, smart routing, disciplined workflow, multi-AI audits -- across every AI coding agent. No BS.

Like ChatGPT's voice conversations with an AI, but entirely offline/private/trade-secret-friendly, using local AI models such as LLama 2 and Whisper

This RAG (Retrieval-Augmented Generation) project is implemented using pure Java. This approach makes it easier to adapt to enterprise-level environments and is more conducive to secondary development.

PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.

A multi agent path planning solution under a warehouse scenario using Q learning and transfer learning.🤖️

LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.

Real-time on-device text-to-image and image-to-image Semantic Search with video stream camera capture using USearch & UForm AI Swift SDKs for Apple devices 🍏

Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems

🚀 100 hyper-specialized AI agents for Claude Code - Transform Claude into your personal tech army with experts in React, AWS, Kubernetes, ML, Security & more

Multi-Agent Deep Reinforcement Learning (MA-DRL) Routing Simulator for satellite networks

A modular MCP server that provides commonly used developer tools for AI coding agents

耗时多年自研高性能golang棋牌AI智能平台，基于最新主流大模型LLM+多agent协同。严禁赌博，否则后果自负！！！

Collection of Claude Code commands and memories for agentic coding.

Find, search, and resume local AI coding-agent sessions across Muse Code, Claude Code, Codex, Antigravity, Grok, Kimi, Qwen, Gemini, Cursor, and more.

思源笔记AI Copilot插件，支持基于思源笔记进行AI问答和编辑，支持agent模式调用工具

SkillWeaver is a framework to enable web agent self-improvement through environment exploration and skill synthesis.

Trading journal with AI agents and dashboard with statistics

A dashboard for running and coordinating multiple AI CLI agents at once.

Agent Skills for the Venice.ai API. One folder per surface area, each with a SKILL.md for agent runtimes (Cursor, Claude, Codex, etc.).

Add CometChat chat & messaging and voice & video calls to any React, Next.js, React Native, Angular, Android, iOS, or Flutter project through your AI coding agent. Works with Claude Code, Cursor, Codex, VS Code Copilot, Windsurf, Cline, Kiro, and 50+ more agents.

Self-hosted, enterprise-ready AI workflow orchestration with event sourcing, CQRS, fault tolerance, and observability. Single-binary control plane, Python + Go SDKs, embedded Postgres + NATS for zero-config dev.

Your smart, reliable, and friendly personal AI assistant.

AI-powered web app generator — turn natural language ideas into full code with live preview and code explorer ｜AI 驱动的 Web 应用生成平台，通过自然语言对话生成完整可运行的代码，并提供实时预览与代码浏览

Self-improving, AI-native markdown vault you hand to an AI agent. GitHub-style file tree + Notion editing, exposed to Claude/Cursor via a built-in MCP server (24 tools): semantic & hybrid search, RAG, cited answers. Learns your voice from your edits; human-approved review queue. Local-first .md.

Cross-platform virtual character immersive interaction engine

Context bomb strings

Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF

📚【更新中】AISecOps: AI-Driven Enterprise Security｜AI 驱动的安全体系。一套将 AI 能力嵌入企业安全体系的方法论框架，以及支撑它落地的完整工程实践——从安全架构、GRC、云原生、数据隐私到 SOC 运营、身份治理与 AI 系统安全。开源中文技术专著，CC BY-NC-SA 4.0。/*⚡🌊🛡️*/

Open-source desktop AI agent: built-in free model, local GGUF models via llama.cpp, dispatch tasks from WeChat/Feishu/DingTalk. Files, browser & MCP tools. | 开源桌面 AI 智能体：内置免费模型，llama.cpp 本地 GGUF 模型，微信/飞书/钉钉直接派任务。

Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.

Islamic-knowledge AI service for DeenBridge — FastAPI + Gemini assistant with verified Qur'an/Hadith citations, scholar-review fallback, and guidance for Stellar/USDC payments.

Disciplined Agentic Engineering — a methodology kit for Claude Code: acceptance-test-first specs, explicit checkpoints, and autonomy you can actually leave running. The engineer, atdd and crap-analyzer plugins.

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Codex · GLM).

MCP server + Skill for WeChat DevTools — lets the AI in your editor compile, preview, debug and auto-test Mini Programs. Windows / macOS, on the official MCP Registry. 微信开发者工具 MCP & Skills

Eleven free Claude skills that run a LinkedIn account: posts off 21 hook formulas, comments, replies, profile score, weekly plan, and a humanizer that strips the AI fingerprint.

This repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".

Lazy, AI chatbot service.

Tensorflow chatbot which is capable of interacting with user through Rest Api, Web interface, GUI and CLI.

Claude-style sub-agents (reviewer, debugger, security) for Codex CLI via a tiny MCP server. Each call spins up a clean context in a temp workdir, injects a persona via AGENTS.md, and runs codex exec --profile <agent> to preserve isolated state.

Provides documentation for calling hundreds of Win32API functions from VFP

Toolkit for Coding Agents to work reliably with repo of any size.

Talk with multiple ChatGPT agents

Multi-Agent Team for Creating Long-form Videos

Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and distribution.

Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper.

Benchmarking LLM agents on Cyber Threat Investigation.

Total conversion for Claude Code. Use RAG and the RPG ruleset apis to play a persistent adventure in any book or world of your choosing.

MiroFish的免费本地运行版本 | Graphiti+Neo4j替代付费Zep | 简易便捷本地跑通

Custom tools to enhance your Open-Webui Experience! 🚀

Find, connect, rediscover your notes — a local-first second brain for Obsidian. Semantic search with strong Chinese/CJK, relation graphs and semantic paths for connections you never drew, Hot/Cold rediscovery of forgotten notes. Desktop builds the index; phones and tablets search it. No API keys.

AI Agency Command Center for Claude Code — orchestrates 5 AI teams (Marketing, Sales, Legal, Reputation, GEO/SEO) into a unified zero-employee agency. 9 skills, 5 parallel agents, composite scoring, and professional PDF reports.

The fastest Office document library for Python, Rust, Go, JS/TS, C# and WASM. DOCX, XLSX, PPTX, DOC, XLS, PPT. Up to 100× faster than python-docx/openpyxl/python-pptx. 100% pass rate on valid Office files. MIT/Apache-2.0.

Chat agents for your team, with approvals and sandboxed tools. Slack, Discord, Telegram, webhooks.

A keyboard-first menubar app to monitor and jump between AI coding sessions — minimum setup required.

One Page Agent.The browser-native workbench that lives in One Page.

An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode, paper: https://arxiv.org/abs/2606.09682

Agent skills for Alpaca's Trading API and Broker API: drop-in SKILL.md files for AI coding assistants

Turn any file into a beautiful, interactive, shareable HTML — WhatsApp logs, PDFs, transcripts, code, anything.

Route complex Codex tasks to model-specific background workers with bounded concurrency and lead-agent verification.

A reusable Agent Skill for designing, reviewing, and implementing UI/UX with Google Material Design 3, Material You, M3 Expressive, accessibility, adaptive layouts, and semantic design tokens.

Source-grounded public context for 立正: Superlinear posts, selected comments, YouTube, Public Axioms V1, and 《真本事》.

Cross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.